From 2ab0796d7a3a7116a79b65531fd33f1548514b52 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Sat, 23 Apr 2011 12:35:41 -0400 Subject: Fix char2wchar/wchar2char to support collations properly. These functions should take a pg_locale_t, not a collation OID, and should call mbstowcs_l/wcstombs_l where available. Where those functions are not available, temporarily select the correct locale with uselocale(). This change removes the bogus assumption that all locales selectable in a given database have the same wide-character conversion method; in particular, the collate.linux.utf8 regression test now passes with LC_CTYPE=C, so long as the database encoding is UTF8. I decided to move the char2wchar/wchar2char functions out of mbutils.c and into pg_locale.c, because they work on wchar_t not pg_wchar_t and thus don't really belong with the mbutils.c functions. Keeping them where they were would have required importing pg_locale_t into pg_wchar.h somehow, which did not seem like a good plan. --- src/backend/utils/adt/formatting.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'src/backend/utils/adt/formatting.c') diff --git a/src/backend/utils/adt/formatting.c b/src/backend/utils/adt/formatting.c index f895bbbb8b9..726a1f45523 100644 --- a/src/backend/utils/adt/formatting.c +++ b/src/backend/utils/adt/formatting.c @@ -1454,6 +1454,10 @@ str_numth(char *dest, char *num, int type) return dest; } +/***************************************************************************** + * upper/lower/initcap functions + *****************************************************************************/ + /* * If the system provides the needed functions for wide-character manipulation * (which are all standardized by C99), then we implement upper/lower/initcap @@ -1527,7 +1531,7 @@ str_tolower(const char *buff, size_t nbytes, Oid collid) /* Output workspace cannot have more codes than input bytes */ workspace = (wchar_t *) palloc((nbytes + 1) * sizeof(wchar_t)); - char2wchar(workspace, nbytes + 1, buff, nbytes, collid); + char2wchar(workspace, nbytes + 1, buff, nbytes, mylocale); for (curr_char = 0; workspace[curr_char] != 0; curr_char++) { @@ -1543,7 +1547,7 @@ str_tolower(const char *buff, size_t nbytes, Oid collid) result_size = curr_char * pg_database_encoding_max_length() + 1; result = palloc(result_size); - wchar2char(result, workspace, result_size, collid); + wchar2char(result, workspace, result_size, mylocale); pfree(workspace); } #endif /* USE_WIDE_UPPER_LOWER */ @@ -1648,7 +1652,7 @@ str_toupper(const char *buff, size_t nbytes, Oid collid) /* Output workspace cannot have more codes than input bytes */ workspace = (wchar_t *) palloc((nbytes + 1) * sizeof(wchar_t)); - char2wchar(workspace, nbytes + 1, buff, nbytes, collid); + char2wchar(workspace, nbytes + 1, buff, nbytes, mylocale); for (curr_char = 0; workspace[curr_char] != 0; curr_char++) { @@ -1664,7 +1668,7 @@ str_toupper(const char *buff, size_t nbytes, Oid collid) result_size = curr_char * pg_database_encoding_max_length() + 1; result = palloc(result_size); - wchar2char(result, workspace, result_size, collid); + wchar2char(result, workspace, result_size, mylocale); pfree(workspace); } #endif /* USE_WIDE_UPPER_LOWER */ @@ -1781,7 +1785,7 @@ str_initcap(const char *buff, size_t nbytes, Oid collid) /* Output workspace cannot have more codes than input bytes */ workspace = (wchar_t *) palloc((nbytes + 1) * sizeof(wchar_t)); - char2wchar(workspace, nbytes + 1, buff, nbytes, collid); + char2wchar(workspace, nbytes + 1, buff, nbytes, mylocale); for (curr_char = 0; workspace[curr_char] != 0; curr_char++) { @@ -1809,7 +1813,7 @@ str_initcap(const char *buff, size_t nbytes, Oid collid) result_size = curr_char * pg_database_encoding_max_length() + 1; result = palloc(result_size); - wchar2char(result, workspace, result_size, collid); + wchar2char(result, workspace, result_size, mylocale); pfree(workspace); } #endif /* USE_WIDE_UPPER_LOWER */ -- cgit v1.2.3